Home / AIO Classes / Network / Recurrent Neural Network

Recurrent Neural Network

Network AIO:RecurrentNeuralNetwork NOT_REVIEWED

A network with connections forming a directed graph along a temporal sequence enabling dynamic behavior.

Ontology IRI: https://w3id.org/aio/RecurrentNeuralNetwork

Ontology Structure & Relationships

Parent Classes

AIO:Network (Network)

Branches

Network

Annotations & Sources

Synonyms:

RN exact
RecNN exact
Recurrent Network exact

Subsets:

https://w3id.org/aio/NetworkSubset

Curated AIMech Concepts Grounded to this Class

24 Concepts

Curated Concept	Kind	Mapping Relation	Rationale
Clockwork recurrent neural network `AIMech:ClockworkRecurrentNeuralNetwork`	Architectures	broad_match	This is a recurrent sequence architecture with prescribed module clocks and constrained inter-module connectivity; the target is the broader recurrent architecture category.
Deep Output Recurrent Neural Network `AIMech:DeepOutputRecurrentNeuralNetwork`	Architectures	broad_match	The local architecture is a specific recurrent network with an MLP output map; the pinned generic RNN target is broader.
Deep Output-Transition Recurrent Neural Network `AIMech:DeepOutputTransitionRecurrentNeuralNetwork`	Architectures	broad_match	The local architecture is a particular recurrent sequence network with deep transition and output maps; the pinned generic RNN target is broader.
Deep Transition Recurrent Neural Network `AIMech:DeepTransitionRecurrentNeuralNetwork`	Architectures	broad_match	The local architecture is defined by a specific deep recurrent transition; the pinned generic RNN target is broader.
Dynamic Memory Network `AIMech:DynamicMemoryNetwork`	Architectures	broad_match	The architecture recurrently encodes word sequences and uses recurrent episodic and answer states. The pinned recurrent-network concept is broader than this specific arrangement.
Dynamic Memory Network Plus `AIMech:DynamicMemoryNetworkPlus`	Architectures	broad_match	Bidirectional input fusion and the attention-based recurrent fact scan define a specific recurrent architecture; the target is broader.
Gamma neural model `AIMech:GammaNeuralModel`	Architectures	broad_match	The gamma family realizes temporal state through recursive memory dynamics. Even the focused configuration has recurrent memory feeding a spatially feedforward mapper. The AIO recurrent-network category is broader than this particular gamma-kernel architecture family.
Gated-feedback recurrent neural network `AIMech:GatedFeedbackRecurrentNeuralNetwork`	Architectures	broad_match	This is a recurrent sequence architecture with gated inter-layer temporal connections; the target is the broader recurrent architecture category.
Identity-initialized rectified recurrent neural network `AIMech:IdentityInitializedRecurrentNeuralNetwork`	Architectures	broad_match	IRNN is a recurrent sequence network with a specific activation and initial-parameter convention. The AIO target denotes the broader recurrent architecture category.
Input-output hidden Markov model `AIMech:InputOutputHiddenMarkovModel`	Model Families	related_match	The original realization is a modular recurrent neural architecture whose state distribution gates static subnetworks. The conditional model family also admits tabular parameterizations, so this records the architectural association rather than claiming every IOHMM is a neural network.
Inverse compositional spatial transformer network `AIMech:InverseCompositionalSpatialTransformerNetwork`	Architectures	related_match	The architecture reuses a learned predictor with feedback through accumulated geometric state over alignment iterations, supporting a qualified relation to the pinned recurrent-network class. These are computational alignment iterations and need not represent observations in a temporal input sequence. The relation does not assert exact identity or subclass membership, and it does not turn the attention-based Transformer name into a match.
List-augmented recurrent neural network `AIMech:ListAugmentedRecurrentNeuralNetwork`	Architectures	broad_match	The architecture is a recurrent sequence network with a particular external-list access topology; the AIO target is the broader recurrent architecture category.
Mamba sequence architecture `AIMech:Mamba`	Architectures	related_match	Selective state updates use a temporal recurrence, but this mapping does not equate all recurrent networks with Mamba.
Neural GPU `AIMech:NeuralGPU`	Architectures	broad_match	Shared gated state evolution across computational time defines a specific recurrent neural architecture; an observed temporal input stream is not required.
Neural network pushdown automaton `AIMech:NeuralNetworkPushdownAutomaton`	Architectures	broad_match	NNPDA combines recurrent state dynamics with a particular external fractional stack and controller; the AIO target is the broader recurrent architecture category.
Norm-stabilizer `AIMech:NormStabilizer`	Algorithms	related_match	The penalty regularizes sequences of recurrent states. The target denotes the architecture context rather than this training procedure.
RNN-NADE `AIMech:RecurrentNeuralNetworkNeuralAutoregressiveDistributionEstimator`	Architectures	broad_match	The pinned AIO target is broader than this explicit recurrent neural architecture with a specified conditional-density output. The deterministic state has directed temporal connections; the output estimator adds a narrower structural restriction. A temporal probability model over vector frames is not necessarily an autoregressive language model.
RNN-RBM `AIMech:RecurrentNeuralNetworkRestrictedBoltzmannMachine`	Architectures	broad_match	The pinned AIO target is broader than this explicit recurrent neural architecture with a specified conditional-density output. The deterministic state has directed temporal connections; the output estimator adds a narrower structural restriction. A temporal probability model over vector frames is not necessarily an autoregressive language model.
Recurrent temporal restricted Boltzmann machine `AIMech:RecurrentTemporalRestrictedBoltzmannMachine`	Architectures	broad_match	The pinned target is broader: a neural network with directed temporal connections. RTRBM has an explicit deterministic recurrent update and a recurrent-network likelihood objective, with the additional defining restriction that its tied conditional RBM marginal supplies the output distribution. This is a structural mapping, not equivalence to every recurrent network or an empirical performance claim.
Stack-augmented recurrent neural network `AIMech:StackAugmentedRecurrentNeuralNetwork`	Architectures	broad_match	The architecture is a recurrent sequence model with a particular external-memory topology; the target is the broader recurrent architecture category.
Structurally constrained recurrent neural network `AIMech:StructurallyConstrainedRecurrentNeuralNetwork`	Architectures	broad_match	The architecture is a recurrent sequence network with a constrained linear context subsystem; the target is the broader recurrent architecture category.
Temporal-kernel recurrent neural network `AIMech:TemporalKernelRecurrentNeuralNetwork`	Architectures	broad_match	Temporal-kernel traces participate in nonlinear recurrent sequence dynamics; the AIO target is the broader recurrent architecture category.
Vanishing gradient regularization `AIMech:VanishingGradientRegularization`	Algorithms	related_match	The procedure regularizes error transport through recurrent state transitions. The target denotes the network architecture context, not the regularization algorithm itself.
Zoneout `AIMech:Zoneout`	Algorithms	related_match	Zoneout modifies a recurrent state transition. The AIO target denotes the broader network architecture category, not this stochastic regularization algorithm.

Import Provenance & Upstream Synchronization

Source Repo: AIO GitHub

Release Version: aio.json

Commit: 397851c547…

License: CC-BY-4.0

Imported At: 2026-10-10T07:34:10Z

SHA256: 8f741d71408c…

Source File: data/aio/RecurrentNeuralNetwork.yaml